LCR Leaderboard

Long Context Retrieval benchmark testing ability to find and use information in very long documents.

Data from Artificial Analysis

As of November 21, 2026, the top-scoring model on LCR is Kimi K3 at 88.7%, followed by MiMo v2.6 Pro at 86.3% and Kimi K3.1 Pro at 86.3%. 274 models have been evaluated on this benchmark.

Last updated: November 21, 2026

8 Ways to Use Fewer Tokens

Models

274

Best Score

88.7

Average

51.6

Std Dev

27.9

Categories
Reasoning and Logic
Sponsored The Grid | Spot Priced LLM API
The Grid | Spot Priced LLM API — Why pay list price when providers will bid for your API usage? Up to 80% off.
View spot prices
Provider
Model
Input $/M
Output $/M
LCR
Actions
$0.180
$9.500
88.7
$0.326
$0.652
86.3
$0.240
$6.000
86.3
$10.000
$50.000
85.3
$5.000
$30.000
84.3
$1.250
$4.250
84.3
$2.000
$10.000
84.0
$0.040
$0.100
84.0
$0.200
$1.200
83.7
$1.750
$14.000
83.3
$0.050
$0.200
83.3
$0.230
$0.960
83.0
$2.000
$12.000
83.0
$10.500
$84.000
82.7
$2.000
$10.000
82.7
$0.100
$0.500
82.7
$1.000
$5.000
82.7
$1.750
$14.000
82.3
$10.000
$50.000
82.3
$1.000
$6.000
82.0
$1.250
$7.500
82.0
$2.000
$10.000
82.0
$0.035
$0.900
82.0
$0.250
$1.000
81.7
$0.750
$3.750
81.7
$0.216
$0.647
81.3
$0.750
$3.750
81.3
$0.700
$2.100
81.3
$0.000
$0.000
81.0
$2.000
$6.000
81.0
$5.000
$25.000
80.7
$0.111
$1.322
80.3
$2.000
$6.000
80.3
$0.900
$0.900
80.3
$0.625
$5.000
80.0
$3.000
$15.000
80.0
$0.750
$3.750
80.0
$0.040
$0.078
80.0
$0.480
$1.800
79.7
$0.014
$0.029
79.7
$0.070
$1.400
79.7
$2.000
$10.000
79.7
$0.135
$0.400
79.7
$0.400
$1.760
79.3
$0.600
$3.000
79.3
$2.000
$6.000
79.3
$5.000
$25.000
79.3
$1.000
$5.000
79.3
$1.475
$4.425
79.0
$0.132
$0.528
79.0
$0.100
$0.200
79.0
$5.000
$25.000
78.7
$0.000
$0.000
78.3
$0.007
$0.950
78.3
$0.060
$0.180
78.3
$1.250
$4.250
78.3
$1.250
$10.000
78.2
$0.500
$3.000
78.0
$0.490
$2.500
78.0
$5.000
$25.000
78.0
$0.195
$0.900
77.7
$5.000
$25.000
77.7
$5.000
$25.000
77.3
$0.390
$0.900
77.3
$0.250
$0.900
77.3
$1.000
$4.050
77.3
$0.375
$2.250
77.0
$0.100
$0.625
76.7
$2.000
$6.000
76.7
$0.260
$0.900
76.3
$15.000
$75.000
76.0
$2.000
$12.000
76.0
$0.300
$2.500
76.0
$0.600
$1.920
75.7
$0.450
$1.200
75.7
$0.400
$2.000
75.0
$2.000
$8.000
74.7
$1.000
$5.000
74.3
$0.780
$3.900
74.3
$0.250
$1.500
74.3
$1.500
$9.000
74.3
$0.100
$0.224
74.3
$0.000
$0.000
74.0
$0.150
$0.600
74.0
$0.200
$0.500
73.7
$0.899
$2.825
73.7
$0.200
$1.150
73.7
$0.042
$0.123
73.7
$0.209
$0.310
73.3
$0.270
$0.950
73.3
$0.300
$1.200
73.0
$0.320
$1.280
73.0
$0.021
$0.063
73.0
$0.125
$1.000
72.3
$0.270
$0.410
72.3
$3.000
$15.000
72.3
$0.550
$2.200
72.0
$0.450
$0.900
72.0
$0.065
$0.750
72.0
$1.250
$10.000
71.7
$1.200
$4.000
71.7
$0.050
$0.700
71.7
$0.040
$0.150
71.7
$0.090
$0.290
71.3
$0.320
$1.400
71.0
$5.000
$25.000
70.7
$0.090
$0.290
70.7
$3.000
$15.000
70.3
$1.750
$14.000
70.3
$1.200
$4.000
70.3
$0.270
$0.400
70.0
$0.080
$0.120
70.0
$0.100
$0.100
69.7
$15.000
$75.000
69.3
$0.270
$1.000
69.3
$1.250
$10.000
69.3
$1.500
$7.500
69.3
$1.000
$10.000
69.0
$2.000
$8.000
68.3
$3.000
$15.000
68.0
$0.300
$1.200
67.7
$0.490
$2.500
67.3
$5.000
$25.000
67.0
$0.250
$2.000
66.7
$0.050
$0.190
65.7
$0.300
$2.500
65.3
$15.000
$60.000
65.0
$1.250
$10.000
65.0
$0.300
$1.200
65.0
$0.100
$0.400
64.7
$0.180
$0.600
64.7
$0.300
$1.200
64.3
$0.150
$0.900
63.7
$0.900
$0.900
63.7
$0.090
$0.300
63.0
$0.780
$3.900
62.0
$0.200
$0.900
61.3
$1.100
$4.400
61.0
$0.020
$0.096
60.3
$3.000
$15.000
58.0
$0.550
$2.190
57.7
$0.000
$0.000
57.7
$0.250
$0.950
56.7
$0.500
$2.150
55.7
$0.100
$0.400
55.7
$0.250
$0.500
55.3
$0.500
$0.900
55.3
$0.500
$3.000
55.3
$3.000
$15.000
54.0
$0.430
$1.750
54.0
$0.200
$1.500
53.0
$0.600
$2.500
53.0
$0.600
$2.200
52.7
$0.090
$0.900
52.7
$0.300
$1.500
52.7
$0.030
$0.100
52.0
$3.000
$15.000
51.7
$0.200
$0.600
50.0
$0.780
$3.900
50.0
$0.300
$2.500
49.9
$0.100
$0.400
49.7
$1.000
$5.000
49.7
$0.300
$0.900
48.7
$0.250
$0.950
47.0
$0.120
$0.800
47.0
$0.130
$0.850
46.7
$0.300
$0.900
45.7
$0.209
$0.310
45.7
$0.270
$1.000
45.3
$0.025
$0.200
45.0
$0.060
$0.150
45.0
$0.270
$0.410
44.7
$0.400
$1.600
44.0
$3.000
$15.000
44.0
$0.600
$1.920
43.7
$0.250
$0.750
43.7
$1.100
$4.400
43.0
$0.440
$2.200
42.7
$0.060
$0.400
41.7
$0.075
$0.625
41.7
$2.500
$10.000
41.0
$0.200
$0.200
41.0
$0.250
$1.000
40.7
$0.320
$1.400
40.7
$0.200
$1.100
39.7
$0.207
$0.828
38.7
$0.060
$0.240
38.0
$0.200
$0.200
37.3
$0.017
$0.085
34.7
$2.500
$12.500
34.3
$0.000
$0.000
33.9
$0.117
$1.365
33.3
$0.070
$0.280
32.7
$0.200
$0.880
32.7
$0.400
$0.900
32.3
$0.150
$0.600
32.3
$0.400
$2.000
32.0
$0.100
$0.400
32.0
$0.150
$0.600
31.3
$0.440
$2.200
31.3
$0.000
$0.000
31.3
$0.010
$0.030
31.3
$0.100
$0.300
27.7
$0.250
$1.250
27.7
$0.800
$4.000
27.3
$0.900
$0.900
26.7
$0.090
$0.300
26.3
$0.430
$1.750
26.3
$0.200
$0.200
26.3
$0.150
$0.150
25.7
$1.500
$1.500
25.3
$0.000
$0.000
24.7
$0.060
$0.200
24.0
$0.200
$0.500
24.0
$0.060
$0.200
22.7
$0.900
$0.900
22.7
$0.100
$0.300
22.3
$1.000
$3.000
22.3
$1.000
$3.000
22.0
$2.500
$10.000
21.3
$0.800
$3.200
21.0
$0.200
$0.200
20.7
$0.100
$0.400
20.3
$0.075
$0.200
20.3
$0.060
$0.400
20.3
$2.000
$8.000
19.3
$0.060
$0.240
19.0
$0.070
$0.280
18.7
$0.300
$2.500
18.7
$0.000
$0.000
18.3
$0.020
$0.040
18.0
$0.300
$0.900
17.0
$0.180
$0.200
16.7
$0.100
$0.320
15.7
$0.035
$0.140
13.0
$0.060
$0.060
12.7
$0.200
$0.200
11.3
$0.060
$0.240
10.7
$0.750
$0.800
10.0
$0.093
$0.373
9.7
$0.300
$0.300
8.7
$0.880
$0.880
8.3
$0.050
$0.150
8.3
$0.080
$0.160
7.3
$0.020
$0.020
6.7
$0.040
$0.050
6.7
$0.350
$0.500
5.7
$0.093
$0.373
4.7
$0.030
$0.050
4.3
$2.000
$6.000
2.0
$0.510
$0.740
-
$0.040
$0.040
-
$0.070
$0.140
-
$0.040
$0.064
-
$0.050
$0.200
-
$0.900
$0.900
-
$0.900
$0.900
-
$0.064
$0.224
-
$0.064
$0.224
-
$0.080
$0.200
-
$0.080
$0.200
-
$0.200
$0.200
-
$0.200
$0.200
-
$0.120
$0.500
-
$0.120
$0.500
-
$0.000
$0.000
-
$0.600
$1.800
-
$0.600
$1.800
-
$0.120
$0.200
-
$0.100
$0.200
-
$0.150
$0.500
-
$0.150
$0.500
-
$0.200
$0.600
-
$0.200
$0.200
-

Pricing from OpenRouter. Benchmarks from Artificial Analysis.

About LCR

Long Context Retrieval benchmark testing ability to find and use information in very long documents.

This leaderboard shows all models with LCR benchmark scores, ranked from highest to lowest. Pricing data is included to help you compare performance against cost.

Frequently Asked Questions

Long Context Retrieval benchmark testing ability to find and use information in very long documents.
As of November 21, 2026, Kimi K3 leads the LCR leaderboard with a score of 88.7. Rankings change as new models are released and evaluated.
Currently 274 models have been evaluated on LCR, with an average score of 51.6 and standard deviation of 27.9.
Benchmark scores are updated when new evaluations are published by our data sources (Artificial Analysis and LayerLens). Pricing data is refreshed daily from OpenRouter.